Related papers: Open Set Recognition using Vision Transformer with…

Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-world scenarios where there are test samples of unknown classes…

Vision Transformers (ViTs) have achieved remarkable success over various vision tasks, yet their robustness against data distribution shifts and inherent inductive biases remain underexplored. To enhance the robustness of ViT models for…

Transformers are state-of-the-art deep learning models that are composed of stacked attention and point-wise, fully connected layers designed for handling sequential data. Transformers are not only ubiquitous throughout Natural Language…

Though vision transformers (ViTs) have achieved state-of-the-art performance in a variety of settings, they exhibit surprising failures when performing tasks involving visual relations. This begs the question: how do ViTs attempt to perform…

Existing synthetic aperture radar automatic target recognition (SAR ATR) methods have been effective for the classification of seen target classes. However, it is more meaningful and challenging to distinguish the unseen target classes,…

Land cover classification of satellite imagery is an important step toward analyzing the Earth's surface. Existing models assume a closed-set setting where both the training and testing classes belong to the same label set. However, due to…

In real-world scenarios classification models are often required to perform robustly when predicting samples belonging to classes that have not appeared during its training stage. Open Set Recognition addresses this issue by devising models…

Side-scan sonar (SSS) imagery presents unique challenges in the classification of man-made objects on the seafloor due to the complex and varied underwater environments. Historically, experts have manually interpreted SSS images, relying on…

Fine-grained classification is a challenging task that involves identifying subtle differences between objects within the same category. This task is particularly challenging in scenarios where data is scarce. Visual transformers (ViT) have…

Artificial intelligence (AI) based device identification improves the security of the internet of things (IoT), and accelerates the authentication process. However, existing approaches rely on the assumption that we can learn all the…

Optical Coherence Tomography (OCT) provides high-resolution cross-sectional images useful for diagnosing various diseases, but their distinct characteristics from natural images raise questions about whether large-scale pre-training on…

Most face identification approaches employ a Siamese neural network to compare two images at the image embedding level. Yet, this technique can be subject to occlusion (e.g. faces with masks or sunglasses) and out-of-distribution data.…

Recently, the vision transformer (ViT) has made breakthroughs in image recognition. Its self-attention mechanism (MSA) can extract discriminative labeling information of different pixel blocks to improve image classification accuracy.…

Vision Transformers (ViTs) are widely adopted in medical imaging tasks, and some existing efforts have been directed towards vision-language training for Chest X-rays (CXRs). However, we envision that there still exists a potential for…

In this paper, we consider the problem of simultaneously detecting objects and inferring their visual attributes in an image, even for those with no manual annotations provided at the training stage, resembling an open-vocabulary scenario.…

We propose an adaptation to the training of Vision Transformers (ViTs) that allows for an explicit modeling of objects during the attention computation. This is achieved by adding a new branch to selected attention layers that computes an…

The findings on open-set recognition (OSR) show that models trained on classification datasets are capable of detecting unknown classes not encountered during the training process. Specifically, after training, the learned representations…

Transformers are transforming the landscape of computer vision, especially for recognition tasks. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the first fully…

Recently, several Vision Transformer (ViT) based methods have been proposed for Fine-Grained Visual Classification (FGVC).These methods significantly surpass existing CNN-based ones, demonstrating the effectiveness of ViT in FGVC…

We present Region-aware Open-vocabulary Vision Transformers (RO-ViT) - a contrastive image-text pretraining recipe to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretraining phase, we propose…